Neural Network PID Controller Research Articles

AMESim simulation and energy control of hydraulic control system for direct drive electro-hydraulic servo die forging hammer

The application of direct drive electro-hydraulic servo system in die forging hammer is studied, and a new type of direct drive electro-hydraulic servo control die forging hammer is proposed. The impact energy of forging hammer is modelled by analytic method, and the relationship between impact energy E and motor speed n is simulated and analysed by Simulink software. The AC permanent magnet synchronous servo motor model and the hydraulic system simulation model are established on AMESim, and the system performance curve, the pump output flow curve and the servo motor speed curve are obtained. A wavelet neural network PID control algorithm is proposed to realise closed-loop control of pressure and speed of direct drive electro-hydraulic servo die forging hammer. A combined simulation model of AMESim and Simulink is built. The hardware-in-the-loop simulation experiment of the control system is designed. The simulation and experimental results verify the correctness of the scheme.

Modeling and Simulation of Energy‐Regenerative Active Suspension Based on BP Neural Network PID Control

In this paper, an electromagnetic energy‐regenerative suspension system is proposed to achieve active control and vibration energy harvesting. For this system, a PID controller based on BP neural network algorithm is designed and vehicle dynamic performances are studied. Based on the traditional energy‐regenerative efficiency calculation, a novel self‐supply energy efficiency concept is proposed to evaluate the utilization effect of the recycled energy for this dual‐functional suspension. Simulations are carried out, and the results show that the vehicle dynamic performances are effectively improved under different input conditions, including road surfaces and vehicle speeds. Furthermore, the energy‐regenerative suspension can recover part of vibration energy, where the self‐supply energy efficiency is about 55% and the energy‐regenerative efficiency is about 16%. Meanwhile, the BP‐PID algorithm also enables the suspension system’s self‐adaptability and stability characteristics on its energy recovery capability.

An intelligent dc current minimization method for transformerless grid-connected photovoltaic inverters

Due to the scaling and zero-drift of current sensor errors, unbalanced grid voltages, tolerance of power switching devices, and asymmetry of PWM gate driving pulses, transformerless grid-connected inverters usually have certain amount of dc components injected to the ac grid. Therefore, power quality of the grid is degraded. Many efforts, such as using blocking capacitors, a dc current feedback control method, and a voltage dc component feedback control method, etc., have been introduced to minimize the dc injection. This paper proposes an intelligent control strategy of dc current injection suppression to the grid by utilizing adaptive-back-propagation (ABP) neural network PID controller. The performance of the proposed scheme is evaluated and compared with the traditional and existing method. Finally, the control scheme is verified on a 2-kW three-phase grid-connected inverter in the laboratory.

Design and Experimental Analysis on Autonomous Control System of Wave Glider

In order to realize the unattended and autonomous navigation of Wave Glider in the ocean, an autonomous control system is designed, which mainly includes the control circuit part, motor driver part and control algorithm part. System integrates solar energy charging module, wireless communication module, satellite communication module, rudder motor module and data acquisition module etc. In order to improve the intelligence and autonomy, the algorithm of Gaussian earth algorithm, visual tracking algorithm and BP neural network PID control algorithm are used to ensure the navigation accuracy of Wave Glider. To verify the reliability of the system, Wave Glider is tested in the ocean in the aspects of long time running, target points tracking, velocity keeping, and data acquisition. The experiment shows that under normal ocean conditions, Wave Glider can realize the long term autonomous navigation tracking in the ocean, but the speed fluctuates significantly by the current ocean condition; The acquisition of sensor data is normal, stable and reliable, which meets the requirement of long term using in the ocean.

Intelligent control of active shock absorber for high-speed elevator car

Due to the influencing factors, such as irregularity of guide, piston wind excitation in the hoistway, and uncertain swinging of hoisting rope during the operation of high-speed traction elevator, car will produce dramatic horizontal vibration. With the purpose of suppressing this vibration effectively, the active car shock absorber is designed with linear motor, and a five-degrees-of-freedom space vibration model of the car is established and, subsequently, its state space equation is derived. For the uncertainty external excitation in the car system, the back propagation neural network proportional–integral–derivative controller with linear prediction model is designed for the intelligent active control of the vibration of the car, and simulation analysis is carried out with MATLAB/Simulink. The result shows that the active shock absorber designed in this study can effectively suppress the horizontal vibration of high-speed elevator car, better than traditional proportional–integral–derivative controller. This study has opened up a new idea of high-speed elevator vibration damping method, and is of important referential significance for the field of active control of car vibration.

Mars entry fault-tolerant control via neural network and structure adaptive model inversion

The capability of autonomous fault detection and reconstruction is essential for future manned Mars exploration missions. Considering actuator failures and atmosphere uncertainties, we present a new active fault-tolerant control algorithm for Mars entry by use of neural network and structure adaptive model inversion. First, the online BP neural network is adopted to conduct the fault detection and isolation. Second, based on the structure adaptive model inversion, an adaptive neural network PID controller is developed for Mars entry fault-tolerant control. The normal PID controller will be automatically switched into neural network PID controller when an actuator fault is detected. Therefore, the error between the reference model and the output of the attitude control system would be adjusted to ensure the dynamic property of the entry vehicle. Finally, the effectiveness of the algorithm developed in this paper is confirmed by computer simulation.

Motion control of linear induction motor based on optimal recurrent wavelet neural network-PID controller

This paper contains a proposed controller based on optimal recurrent wavelet neural network (RWNN) with PID controller to control the velocity and hence the stator current as well as the developed thrust of three phase linear induction motor (LIM) which consider the end effects. A vector control represented by indirect field oriented control (IFOC) technique is appointed to attain velocity and flux control for different loading conditions. Moreover, a voltage source inverter based on space vector pulse width modulation (SVPWM) is utilized to give the required stator voltage of LIM. A well-known particle swarm optimization (PSO) algorithm is employed for online tuning of the proposed controller. The computer simulation results show that this controller is effective and gives preferable and rigorous performance compared with a results obtained from conventional wavelet neural network (WNN) and PID controllers.

Design of neural network PID controller based on E‐FRIT

AbstractProportional–integral–derivative (PID) controllers have been widely used for process systems. However, a good control result is not always obtained with fixed PID gains when a controlled object has nonlinearity. This paper proposes a design method for a nonlinear PID controller that utilizes a neural network to overcome the problem. In the proposed controller, PID gains are tuned online by a neural network and a controlled object is manipulated by the PID controller with the tuned PID gains. The neural network is learned by an offline learning algorithm based on the Extended Fictitious Reference Iterative Tuning (E‐FRIT) and the backpropagation. E‐FRIT is a method that tunes control parameters directly by using operating data and evaluates not only a controlled output but also the difference of manipulated variable. Simulation examples are provided to show the effectiveness of the proposed method. Moreover, the experimental result of a level control of a tank system is also given to demonstrate the performance of the proposed method.

Cutting Constant Power Speed-adjusting Control System of Electrical Haulage Shearer Based on Rbf Neural Network Pid Control

According to the characteristics of electrical haulage shearer in the process of coal mining and the basic principle of cutting constant power speed-adjusting of electrical haulage shearer, taking the traction motor as the controlled object, and cutting constant power speed-adjusting control method of electrical haulage shearer based on RBF neural network PID control is proposed. Adaptive control method to achieve the electrical haulage shearer constant power speed-adjusting and high precision control. At the same time, improve the efficiency of coal mining, to ensure the safety of the shearer. The modeling and simulation analysis of the cutting constant power speed-adjusting control system of electrical haulage Shearer are carried out by Matlab/Simulink, and the system through the field experiment and the comparative analysis with traditional fuzzy PID control. The results show that the system based on RBF neural network PID control has stronger anti-interference ability, higher control precision, faster response time, stronger practicability and stability.

System modeling and instability control of wind turbine blade based on hydraulic pitch system and radial basic function neural network proportional–integral–derivative controller

System modeling and aeroservoelastic control for divergent instability of stall-induced composite wind turbine blade modeled as thin-walled symmetric layup beam analysis have been investigated based on hydraulic pitch system and radial basic function neural network control. The blade is modeled as single-cell thin-walled beam structure with the circumferentially asymmetric stiffness design, exhibiting flap/lead-lag bending coupling deformation. The stall flutter and aeroservoelastic control of composite blade are investigated based on dynamic stall Beddoes–Leishman aerodynamic model and radial basic function neural network proportional–integral–derivative controller, with pitch actuator performed by hydraulic system. The system motion equations consist of the aeroelastic equations and the six-order pitch equation. The nonlinear aeroelastic responses, including both flap/lead-lag responses and pitch angle responses under different parameters, are solved by Galerkin method and the nonlinear time integration scheme with nonlinear residual analysis. To verify the effectiveness of the control scheme and realize visualized display of large thin-walled blade in the laboratory, experimental platform based on hardware-in-the-loop simulation is built to realize real-time control and virtual simulation. The platform structure consists of PLC hardware, monitoring interface in configuration software, and simulation environment that is connected by the OPC server with PLC system. The platform lays the foundation for vibrational behavior research on visualization of large wind turbine blade under divergent stall situation and verifies the real-time feasibility of the control algorithm proposed.

Enhance Cascaded H-Bridge Multilevel Inverter with Artificial Intelligence Control

This paper proposed a 7-level Cascaded H-Bridge Multilevel Inverter (CHBMI) with two diffenrent controller, ie, PID and Artificial Neural Network (ANN) controller to improve the output voltage performance and achieve a lower Total Harmonic Distortion (THD). A PWM generator is connected to the 7-level CHBMI to provide switching of the MOSFET. The reference signal waveform for the PWM generator is set to be sinusoidal to obtain an ideal AC output voltage waveform from the CHBMI. By tuning the PID controller as well as the self-learning abilities of the ANN controller, switching signals towards the CHBMI can be improved. Simulation results from the general CHBMI together with the proposed PID and ANN controller based 7-level CHBMI models will be compared and discussed to verifyl the proposed ANN controller based 7-level CHBMI achieved a lower output voltage THD value with a better sinusoidal output performance.

Control of Switched Reluctance Motors based on Improved BP Neural Networks

Background: Switched reluctance motors have a strong nonlinear performance due to their structure and operation mode. The performance and control strategy of this kind of motor are obviously different from those traditional strategies. As a result, the accurate model and high performance control of the switched reluctance motor prove to be very important and has obtained wide researches. Method: A kind of switched reluctance motor based on PID neural network control strategy is proposed, which combines artificial fish swarm and particle swarm optimization to optimize weights and thresholds of BP neural networks. Results: Speed responses of the improved BP algorithm have no overshoot, have a smooth transition to the steady state and eliminate the oscillation phenomena which is in the PID control. Conclusion: Besides, it reduces time of transient process to improve the response speed. Antiinterference ability and robustness are obviously superior to the PID control. Keywords: Switched reluctance motor, BP neural network, artificial fish swarm, particle swarm optimization, BP algorithm, global optical value.

Design of Neural Network PID Controller based on E-FRIT

Design of Neural Network PID Controller based on E-FRIT

Synchronization Controller for a 3-RRR Parallel Manipulator

A 3-RRR parallel manipulator has been well-known as a closed-loop kinematic chain mechanism in which the end-effector generally a moving platform is connected to the base by several independent actuators. Performance of the robot is decided by performances of the component actuators which are independently driven by tracking controllers without acknowledging information from each other. The platform performance is degraded if any actuator could not be driven well. Therefore, this paper aims to develop an advanced synchronization (SYNC) controller for position tracking of a 3-RRR parallel robot using three DC motor-driven actuators. The proposed control scheme consists of three sliding mode controllers (SMC) to drive the actuators and a supervisory controller named PID-neural network controller (PIDNNC) to compensate the synchronization errors due to system nonlinearities, uncertainties and external disturbances. A Lyapunov stability condition is added to the PIDNNC training mechanism to ensure the robust tracking performance of the manipulator. Numerical simulations have been performed under different working conditions to demonstrate the effectiveness of the suggested control approach.

Design of neural network model-based controller in a fed-batch microbial electrolysis cell reactor for bio-hydrogen gas production

One of major challenge in bio-hydrogen production process by using MEC process is nonlinear and highly complex system. This is mainly due to the presence of microbial interactions and highly complex phenomena in the system. Its complexity makes MEC system difficult to operate and control under optimal conditions. Thus, precise control is required for the MEC reactor, so that the amount of current required to produce hydrogen gas can be controlled according to the composition of the substrate in the reactor. In this work, two schemes for controlling the current and voltage of MEC were evaluated. The controllers evaluated are PID and Inverse neural network (NN) controller. The comparative study has been carried out under optimal condition for the production of bio-hydrogen gas wherein the controller output is based on the correlation of optimal current and voltage to the MEC. Various simulation tests involving multiple set-point changes and disturbances rejection have been evaluated and the performances of both controllers are discussed. The neural network-based controller results in fast response time and less overshoots while the offset effects are minimal. In conclusion, the Inverse neural network (NN)-based controllers provide better control performance for the MEC system compared to the PID controller.

Design of Neural Network PID Controller Based on E-FRIT and Online Learning

Design of Neural Network PID Controller Based on E-FRIT and Online Learning

Research of Oil Pump Control Based On Fuzzy Neural Network PID Algorithm

Abstract In view of the fact that oil pumps exist in the more complex mountains and plains, external temperature, humidity, crude oil characteristics and other adverse factors make the oil pumps control system appear the problem of drift, Fuzzy neural network PID algorithm is studied and designed to realize controling the oil pump system in this paper, combined with the advantages of conventional PID control, fuzzy control and neural network control, the composition and structure of the oil pump control system are analyzed, the model structure and algorithm implementation of fuzzy neural network PID control algorithm are designed in detail. The simulation results show that the control algorithm has good adaptability and anti-interference ability.

Research on Environmental Adjustment of Cloud Ranch Based on BP Neural Network PID Control

In order to make the intelligent ranch management mode replace the traditional artificial one gradually, this paper proposes a pasture environment control system based on cloud server, and puts forward the PID control algorithm based on BP neural network to control temperature and humidity better in the pasture environment. First, to model the temperature and humidity (controlled object) of the pasture, we can get the transfer function. Then the traditional PID control algorithm and the PID one based on BP neural network are applied to the transfer function. The obtained step tracking curves can be seen that the PID controller based on BP neural network has obvious superiority in adjusting time and error, etc. This algorithm, calculating reasonable control parameters of the temperature and humidity to control environment, can be better used in the cloud service platform.

Neural network fuzzy control for enhancing the stability performance of quad-rotor helicopter

Recently, the quad-rotor helicopter has gained increasing attention owing to its very good flexibility, its ability to execute various flight missions even in harsh environments. The quad-rotor helicopter can implement different fight attitudes, which is attributed to the effective control of the motor speed about four propellers. In order to make the quad-rotor helicopter can better finish flight mission, the performance of flight stability then becomes particularly important. A neural network fuzzy control algorithm is proposed in this paper so as to guarantee the stability performance of the quad-rotor helicopter. The proposed algorithm is based on the neural network, which keeps the self-organization and self-learning ability, besides this, it utilizes the strong impression ability of constitutive knowledge as to the fuzzy logic. The proposed control scheme aims to implement good abilities such as describing qualitative knowledge, strong learning mechanism and direct processing about quantitative data of the quad-rotor helicopter. In the practical flight process of the quad-rotor helicopter, while the deviation of position and attitude information become larger, fuzzy control is adopted so as to shorten the overshoot and adjustment time. On the other hand, if the deviation of position and attitude become relatively smaller, neural network PID control will be used so as to reduce the error. Experimental results show that the proposed neural network fuzzy control algorithm exhibits good performance in the flight process of the quad-rotor helicopter.

A New PID Neural Network Controller Design for Nonlinear Processes

In this paper, a novel adaptive tuning method of PID neural network (PIDNN) controller for nonlinear process is proposed. The presented method utilizes an improved gradient descent method to adjust PIDNN parameters where the margin stability will be employed to get high tracking performance and robustness with regard to external load disturbance and parameter variation. Simulation results show the effectiveness of the proposed algorithm compared with other well-known learning methods.